A high-throughput and memory-efficient inference and serving engine for LLMs
Mirrored from https://github.com/tduncan-lum/Nvidia-Optimization-Stack---VLLM.git
Synced Nov 14, 05:30 UTC
[Misc] Update TritonLanguagePlaceholder to have attributes that are used by Flash Linear Attention ops. (#26853)
Co-authored-by: Xudong Ma <mxd@meta.com>
Xudong Ma committed
Oct 15, 2025 at 01:37 UTC
5210dc3940b0f6554a6db46287281d1be9d187ed
1 file changed
+3
vllm/triton_utils/importing.py
+3
@@ -98,3 +98,6 @@ class TritonLanguagePlaceholder(types.ModuleType):
98
self.int64 = None
99
self.int32 = None
100
self.tensor = None
101
+ self.exp = None
102
+ self.log = None
103
+ self.log2 = None